Word level identification of Kannada, Hindi and English scripts from a tri-lingual document.
M. C. PadmaP. A. VijayaPublished in: Int. J. Comput. Vis. Robotics (2010)
Keyphrases
- word level
- document images
- indian languages
- optical character recognition
- machine translation
- language identification
- english text
- character recognition
- document analysis
- cross lingual
- language independent
- word segmentation
- text lines
- source language
- n gram
- sentence pairs
- cross language
- information retrieval
- word sense disambiguation
- machine vision
- information extraction
- sentence level
- language model
- information retrieval systems
- hidden markov models